# LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

arXiv: https://arxiv.org/abs/2504.16078 · HTML: https://mlsanity.com/paper/2504.16078/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 78 of its 107 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 78)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)

## Built on by (most cited first, 30 of 41)

- [ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models](https://mlsanity.com/paper/2505.24864/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning](https://mlsanity.com/paper/2506.19767/) (2025)
- [Kevin: Multi-Turn RL for Generating CUDA Kernels](https://mlsanity.com/paper/2507.11948/) (2025)
- [Formalizing Learning from Language Feedback with Provable Guarantees](https://mlsanity.com/paper/2506.10341/) (2025)
- [The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?](https://mlsanity.com/paper/2601.23045/) (2026)
- [RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format](https://mlsanity.com/paper/2602.22538/) (2026)
- [The Illusion of Stochasticity in LLMs](https://mlsanity.com/paper/2604.06543/) (2026)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models](https://mlsanity.com/paper/2510.20967/) (2025)
- [MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models](https://mlsanity.com/paper/2604.19809/) (2026)
- [ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection](https://mlsanity.com/paper/2508.01724/) (2025)
- [Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories](https://mlsanity.com/paper/2511.07368/) (2025)
- [When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training](https://mlsanity.com/paper/2509.24923/) (2025)
- [Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science](https://mlsanity.com/paper/2510.03413/) (2025)
- [Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games](https://mlsanity.com/paper/2510.18395/) (2025)
- [Large Language Models Develop Novel Social Biases Through Adaptive Exploration](https://mlsanity.com/paper/2511.06148/) (2025)
- [Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment](https://mlsanity.com/paper/2605.21401/) (2026)
- [BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format](https://mlsanity.com/paper/2509.02655/) (2025)
- [Alternatives To Next Token Prediction In Text Generation -- A Survey](https://mlsanity.com/paper/2509.24435/) (2025)
- [A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits](https://mlsanity.com/paper/2601.12945/) (2026)
- [STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks](https://mlsanity.com/paper/2603.05294/) (2026)
- [Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2603.15871/) (2026)
- [PriorZero: Bridging Language Priors and World Models for Decision Making](https://mlsanity.com/paper/2605.12289/) (2026)
- [STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle](https://mlsanity.com/paper/2607.13618/) (2026)
- [Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency](https://mlsanity.com/paper/2508.13654/) (2025)
- [PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs](https://mlsanity.com/paper/2509.20105/) (2025)
- [ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspective](https://mlsanity.com/paper/2509.21134/) (2025)
- [RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback](https://mlsanity.com/paper/2510.04096/) (2025)
- [PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient](https://mlsanity.com/paper/2601.12988/) (2026)

## Abstract (arXiv)

The success of Large Language Models (LLMs) has sparked interest in various agentic applications. A key hypothesis is that LLMs, leveraging common sense and Chain-of-Thought (CoT) reasoning, can effectively explore and efficiently solve complex domains. However, LLM agents have been found to suffer from sub-optimal exploration and the knowing-doing gap, the inability to effectively act on knowledge present in the model. In this work, we systematically study why LLMs perform sub-optimally in decision-making scenarios. In particular, we closely examine three prevalent failure modes: greediness, frequency bias, and the knowing-doing gap. We propose mitigation of these shortcomings by fine-tuning via Reinforcement Learning (RL) on self-generated CoT rationales. Our experiments across multi-armed bandits, contextual bandits, and Tic-tac-toe, demonstrate that RL fine-tuning enhances the decision-making abilities of LLMs by increasing exploration and narrowing the knowing-doing gap. Finally, we study both classic exploration mechanisms, such as ε-greedy, and LLM-specific approaches, such as self-correction and self-consistency, to enable more effective fine-tuning of LLMs for decision-making.